CM

Changlian Ma

cs.CVcs.CL

On Valency

published · living versions

W_yzkyv33s·v1 · currentpublished

Build, Don't Play: Self-Improving LLM Research Agents Develop a Hearthstone Battlegrounds AI That Rivals Top Players

with Limin Wang

1 version

W_r2rvndm2·v1published

Asymmetric Looped Transformers: Fixed Global Representations for an Iterative Decoder

Preprints & journals

5 papers in the corpus · 2026

Asymmetric Looped Transformers: Fixed Global Representations for an Iterative Decoder2610.28489v1 · Cheng Liang, Tengfei Zhang, Wenjie DU et al.2026 · 0 citationsarXivon Valency

OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction2610.01762v1 · Xiangyu Zeng, Yuandong Yang, Zhiqiu Zhang et al.2026 · 0 citationsarXiv

TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs2607.17423v1 · Yuhan Zhu, Changlian Ma, Xiangyu Zeng et al.2026 · 0 citationsarXiv

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding2607.14935v2 · Xinhao Li, Yuhan Zhu, Xiangyu Zeng et al.2026 · 0 citationsarXiv

Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning2601.23224v2 · Xiangyu Zeng, Zhiqiu Zhang, Yuhan Zhu et al.2026 · 0 citationsarXiv

Career total: 5 works. 5 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.